Advancements in generative Artificial Intelligence (AI) hold great promise for automating radiology workflows, yet challenges in interpretability and reliability hinder clinical adoption. This paper presents an automated radiology report generation framework that combines Concept Bottleneck Models (CBMs) with a Multi-Agent Retrieval-Augmented Generation (RAG) system to bridge AI performance with clinical explainability. CBMs map chest X-ray features to human-understandable clinical concepts, enabling transparent disease classification. Meanwhile, the RAG system integrates multi-agent collaboration and external knowledge to produce contextually rich, evidence-based reports. Our demonstration showcases the system's ability to deliver interpretable predictions, mitigate hallucinations, and generate high-quality, tailored reports with an interactive interface addressing accuracy, trust, and usability challenges. This framework provides a pathway to improving diagnostic consistency and empowering radiologists with actionable insights.

The lack of direct involvement of domain experts, due to technical barriers, further delays the acquisition of new training data [7]. To address these challenges, Fails and Olsen [6] introduced interactive machine learning (IML), enabling non-technical users to train ML models using their own data through manual classification or correcting model outputs. Unlike traditional ML, IML allows real-time updates in response to user input, facilitating focused and incremental adjustments [1, 5]. Building on these advancements, Tseng et al. [17] developed Co-ML, a tablet-based application for collaboratively building ML image classification models across multiple devices, focusing on teaching dataset design practices by creating a shared dataset. In this paper, we extend these concepts by proposing a browser-based tool that allows users to collaborate on IML tasks using federated learning.

This fusion can increase efficiency, enhance safety, and improve passenger experience. AI in aviation currently focuses on AI-for-Cabin and non-critical tasks. On the other hand, AI-for-non-Cabin tasks encompass artificial intelligence techniques for the operation of the aircraft, for example, vehicle management or flight control/guidance/management system functions. AI-for-non-Cabin tasks are therefore subject to stringent certification requirements and a thorough and explainable understanding of the target tasks and AI methods to ensure the safety of passengers, flight crew, and aircraft. Moreover, the scope of AI-for-non-Cabin tasks ranges from communication, radar, digital electronics, integrated avionics systems, and navigation, to advanced traffic detection systems, all being considered critical tasks.

The growing adoption and deployment of Machine Learning (ML) systems came with its share of ethical incidents and societal concerns. It also unveiled the necessity to properly audit these systems in light of ethical principles. For such a novel type of algorithmic auditing to become standard practice, two main prerequisites need to be available: A lifecycle model that is tailored towards transparency and accountability, and a principled risk assessment procedure that allows the proper scoping of the audit. Aiming to make a pragmatic step towards a wider adoption of ML auditing, we present a respective procedure that extends the AI-HLEG guidelines published by the European Commission. Our audit procedure is based on an ML lifecycle model that explicitly focuses on documentation, accountability, and quality assurance; and serves as a common ground for alignment between the auditors and the audited organisation. We describe two pilots conducted on real-world use cases from two different organisations and discuss the shortcomings of ML algorithmic auditing as well as future directions thereof.

Over the years, various approaches have been employed to enhance the productivity of knowledge workers, from addressing psychological well-being to the development of personal knowledge assistants. A significant challenge in this research area has been the absence of a comprehensive, publicly accessible dataset that mirrors real-world knowledge work. Although a handful of datasets exist, many are restricted in access or lack vital information dimensions, complicating meaningful comparison and benchmarking in the domain. This paper presents RLKWiC, a novel dataset of Real-Life Knowledge Work in Context, derived from monitoring the computer interactions of eight participants over a span of two months. As the first publicly available dataset offering a wealth of essential information dimensions (such as explicated contexts, textual contents, and semantics), RLKWiC seeks to address the research gap in the personal information management domain, providing valuable insights for modeling user behavior.

Many car accidents are caused by human distractions, including cognitive distractions. In-vehicle human-machine interfaces (HMIs) have evolved throughout the years, providing more and more functions. Interaction with the HMIs can, however, also lead to further distractions and, as a consequence, accidents. To tackle this problem, we propose using adaptive HMIs that change according to the mental workload of the driver. In this work, we present the current status as well as preliminary results of a user study using naturalistic secondary tasks while driving (i.e., the primary task) that attempt to understand the effects of one such interface.

Artificial intelligence may help to make sporting competitions cleaner and fairer in the future. Professor of Business Informatics Wolfgang Maaß and his teams at Saarland University and the German Research Center for Artificial Intelligence are using self-learning computer systems to make it faster and simpler to uncover doping violations. Maaß and his team have been collaborating with the World Anti-Doping Agency WADA on research projects that use AI systems the team had previously developed for Industry 4.0 applications. By feeding these systems with data from doping tests, the systems become increasingly efficient at detecting sporting fraud. Unequal chances, unfair competition, unclean sport – doping doesn't just violate the principle of fairness, sportsmen, and women who use performance-enhancing substances are putting their own health on the line.

Professor of Business Informatics Wolfgang Maaß (photo) and his teams at Saarland University and the German Research Center for Artificial Intelligence are using self-learning computer systems to make it faster and simpler to uncover doping violations. Maaß and his team have been collaborating with the World Anti-Doping Agency WADA on research projects that use AI systems the team had previously developed for Industry 4.0 applications. By feeding these systems with data from doping tests, the systems become increasingly efficient at detecting sporting fraud. Artificial intelligence may help to make sporting competitions cleaner and fairer in the future. Professor of Business Informatics Wolfgang Maaß and his teams at Saarland University and the German Research Center for Artificial Intelligence are using self-learning computer systems to make it faster and simpler to uncover doping violations.

Artificial intelligence may help to make sporting competitions cleaner and fairer in the future. Professor of Business Informatics Wolfgang Maaß and his teams at Saarland University and the German Research Center for Artificial Intelligence are using self-learning computer systems to make it faster and simpler to uncover doping violations. Maaß and his team have been collaborating with the World Anti-Doping Agency WADA on research projects that use AI systems the team had previously developed for Industry 4.0 applications. By feeding these systems with data from doping tests, the systems become increasingly efficient at detecting sporting fraud. Unequal chances, unfair competition, unclean sport – doping doesn't just violate the principle of fairness, sportsmen and women who use performance-enhancing substances are putting their own health on the line.

IMAGE: Smart data packages are providing food producers with greater insight, making production greener and more cost-efficient, but also generating new revenue streams - all thanks to the Evarest platform currently... view more Food production is a complex process involving the careful monitoring and management of raw materials, supply chains, market prices and much more besides. Access to smart data enables food producers to plan intelligently and to optimize their production processes allowing them to produce the required quantities more cheaply and in a more environmentally friendly way. But this data can also be used to create additional revenue streams for producers - something that will be demonstrated at this year's digital edition of Hannover Messe by members of a research consortium led by Professor of Business Informatics Wolfgang Maaß of Saarland University and the German Research Center for Artificial Intelligence (DFKI). In their'Evarest' research project, the team turns proprietary data into a commodity that can be traded securely without disclosing any intellectual property or trade secrets. What is next year's harvest of cocoa beans or strawberries going to be like?